Machine Learning Methods Applied to Cortico-Cortical Evoked Potentials Aid in Localizing Seizure Onset Zones
This work addresses the challenge of improving surgical treatment for drug-resistant epilepsy patients by potentially aiding in SOZ localization, but it is incremental as it builds on prior attempts with CCEPs.
The study tackled the problem of localizing seizure onset zones (SOZ) in drug-resistant epilepsy patients by applying ten machine learning classifiers to cortico-cortical evoked potentials (CCEP) data, establishing the approach as promising for further research.
Epilepsy affects millions of people, reducing quality of life and increasing risk of premature death. One-third of epilepsy cases are drug-resistant and require surgery for treatment, which necessitates localizing the seizure onset zone (SOZ) in the brain. Attempts have been made to use cortico-cortical evoked potentials (CCEPs) to improve SOZ localization but none have been successful enough for clinical adoption. Here, we compare the performance of ten machine learning classifiers in localizing SOZ from CCEP data. This preliminary study validates a novel application of machine learning, and the results establish our approach as a promising line of research that warrants further investigation. This work also serves to facilitate discussion and collaboration with fellow machine learning and/or epilepsy researchers.